Visual servoing from 2D ultrasound using intensity features

Context

We develop a new approach of ultrasound (US) image-based robotic control. In order to avoid any segmentation process and to be robust to changes in the organ topology, the proposed control directly uses the B-scan image provided by the US probe as visual feature. The interaction matrix enabling the control of the six degrees of freedom (DOF) of the system from the image intensity is modeled using the 3D image gradient computed from the US image. As the estimation of this 3D gradient requires additional parallel images, we focus on tracking and local positioning tasks where the interaction matrix can be pre computed at the desired pose and used in the algorithm without being updated.

To address the issue of respiratory motion compensation with a 2D US probe, we propose to take advantage of the known periodicity of the disturbance motion to improve the accuracy of the tracking task. For this purpose, we implement a repetitive predictive controller (R-GPC) in the control loop.

Experimental results:

This video (26.1 MB mpeg-4 file) shows results of tracking of an US cross-section. The internal view of the 2D probe is automatically stabilized, while the observed object undergoes periodical motion applied with a second robotic arm. To take into account the repetitivity of this motion, a predictive controller is implemented in the control law. In the first experiment realized with an abdominal phantom, we show the accuracy of the tracking observed with this predictive conroller. In a second experiment, we propose to use a soft gelatin-made phantom to consider the robustness of the method on deformable structures. known.

This video (5.2 MB mpeg-4 file) shows results of the motion compensation robotic task obtained on organic soft tissue.

References

1. C. Nadeau, A. Krupa, J. Gangloff. Automatic Tracking of an Organ Section with an Ultrasound Probe: Compensation of Respiratory Motion. In Int. Conf. on Medical Image Computing and Computer Assisted Intervention, MICCAI'11, Toronto, Canada, September 2011.
2. C. Nadeau, A. Krupa. Improving ultrasound intensity-based visual servoing: tracking and positioning tasks with 2D and bi-plane probes. In IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, IROS'11, Pages 2837-2842, San Francisco, USA, September 2011.
3. C. Nadeau, A. Krupa. Intensity-based direct visual servoing of an ultrasound probe. In IEEE Int. Conf. on Robotics and Automation, ICRA'11, Pages 5677-5682, Shanghai, China, May 2011.